Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases and prepositions indicating location or position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the latest in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    -0.34
     record
    -0.32
     publicly
    -0.30
     specific
    -0.30
     pot
    -0.29
    Public
    -0.28
     сх
    -0.28
     social
    -0.28
     Teil
    -0.28
    )
    -0.27
    POSITIVE LOGITS
     تضيفلها
    0.85
     kaarangay
    0.82
     оригіналу
    0.77
    RTLR
    0.77
    ValueStyle
    0.76
     autorytatywna
    0.74
    NameInMap
    0.73
    دانشنامهٔ
    0.72
    Geplaatst
    0.70
    abestanden
    0.69
    Act Density 0.024%

    No Known Activations